Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnly, non-destructive, openWorld), and the description layers on non-obvious behavior: a 25-credit cost, free empty slate, free failed call, a hard paid-plan requirement, and the odd/no-date scoping. It even discloses the modeling methodology behind the over-probabilities (goal distribution vs. Poisson), which no structured field provides.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The paywall and scope constraints are front-loaded, and every clause carries information (credits, plan tier, date scope, output shape). It is dense with stacked parentheticals and runs long, but there is no filler sentence to remove.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, return values need not be spelled out, yet the description still surfaces the key business constraints an agent needs: plan eligibility, credit cost, no-date scope, and the exclusion of odds/injury data. Nothing required to decide whether and how to call it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are already fully documented in the schema, including the team-abbreviation example and the name-fragment/accent behavior. The description only restates them as 'Optional team (either side of the game) and player (name fragment) filters', adding no syntax or edge-case detail beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb and resource: the model's projected stat lines for tonight's NHL players, enumerating each skater's goals/assists/points/shots with ranges and each goalie's saves. It also carves out its niche against siblings by declaring 'Numbers only: no odds, prices or injury notes', which separates it from get_odds and get_player_props.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context: 'Paid plans only (not available on the free plan)' and 'Tonight's slate only; no date argument', plus the note that empty slates and failed calls are free. It stops short of explicitly naming an alternative tool for odds-bearing props or historical props, so selection between siblings still requires some inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.